diff --git a/README.md b/README.md index e4c59ae..66dd1ab 100644 --- a/README.md +++ b/README.md @@ -13,13 +13,14 @@ This is the companion site for our paper - "End-to-end Training for Whole Image For our entry in the DREAM2016 Digital Mammography challenge, see this [write-up](https://www.synapse.org/LiShenDMChallenge). This work is much improved from our method used in the challenge. ## Whole image model downloads -A few best whole image models are available for downloading at this Google Drive [folder](https://drive.google.com/open?id=0B1PVLadG_dCKV2pZem5MTjc1cHc). Here is a table for individual downloads: +A few best whole image models are available for downloading at this Google Drive [folder](https://drive.google.com/open?id=0B1PVLadG_dCKV2pZem5MTjc1cHc). YaroslavNet is the DM challenge top-performing team's [method](https://www.synapse.org/#!Synapse:syn9773040/wiki/426908). Here is a table for individual downloads: | Database | Patch Classifier | Top Layers (two blocks) | Single AUC | Augmented AUC | Link | |---|---|---|---|---|---| | DDSM | Resnet50 | \[512-512-1024\]x2 | 0.86 | 0.88 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKSUJYdzNyZjVsZHc) | | DDSM | VGG16 | 512x1 | 0.83 | 0.86 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKYnREWlJQZ2JaSDQ) | | DDSM | VGG16 | \[512-512-1024\]x2 | 0.85 | 0.88 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKdVQzbDRLNTZ4TXM) | +| DDSM | YaroslavNet | heatmap + max pooling + FC16-8 + shortcut | 0.83 | 0.86 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKVk9RM1dMeTkwcTg) | | INbreast | VGG16 | 512x1 | 0.92 | 0.94 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKN0ZxNFdCRWxHRFU) | | INbreast | VGG16 | \[512-512-1024\]x2 | 0.95 | 0.96 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKUnQwYVhOd2NfQlk) | @@ -36,6 +37,7 @@ Several patch classifier models (i.e. patch state) are also available for downlo | Resnet50 | S10 | 0.89 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKMTc2RGV1NGF6bm8) | | VGG16 | S10 | 0.84 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKZUotelJBTzkwaGM) | | VGG19 | S10 | 0.79 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKUHFpeTgwaVFYS1E) | +| YaroslavNet (Final) | S10 | 0.89 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKSlR4V1QwTGdsbGs) | | Resnet50 | S30 | 0.91 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKSW1RZ0NzOVBJWHc) | | VGG16 | S30 | 0.86 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKbjdodnp2SlR2WFU) | | VGG19 | S30 | 0.89 | [download](https://drive.google.com/open?id=0B1PVLadG_dCKNUpGc3Q1dWJ5OGM) |